Citation

Ahmad, Khubab and Em, Poh Ping and Ab Aziz, Nor Azlina (2024) Leveraging OBD II Time Series Data for Driver Drowsiness Detection: A Recurrent Neural Networks Approach. In: 2024 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 26-28 August 2024, Kota Kinabalu, Malaysia.

Text Leveraging OBD II Time Series Data for Driver Drowsiness Detection_ A Recurrent Neural Networks Approach.pdf - Published Version Restricted to Repository staff only Download (617kB)

Abstract

Driver drowsiness is a major concern in the field of road safety, contributing significantly to road accidents and injuries. To address this issue many studies, focus on the development of a driver drowsiness detection system, existing detection system often rely on driver behaviours, physiological signals, and vehicle behaviours but each approach has limitations in terms of accuracy and real-time applicability. This study utilizes OBD-II (On-Board Diagnostic II) sensors’ data, including parameters such as speed, RPM, throttle position, and steering torque, in conjunction with a camera equipped with a pretrained model for effective data labelling. The methodology employed through the conversion of time series data windows. This approach facilitates the utilization of a recurrent neural network (RNN) for classification, leveraging the model's ability to analyse sequential data patterns. Through rigorous training and testing, the integrated model achieves an impressive accuracy of 81.95% in identifying drowsy and normal driving patterns. The obtained results underscore the effectiveness of the integrated model in discerning subtle variations in driving behaviour, demonstrating its potential as a reliable tool for realtime drowsiness detection. The system's impact lies in its ability to save lives and prevent injuries by providing timely warnings or interventions to drowsy drivers, contributing to safer road environments and the overall reduction of drowsiness-related accidents.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Deep Learning, Driver drowsiness, OBD-II Data, Recurrent Neural Network
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	04 Dec 2024 02:31
Last Modified:	04 Dec 2024 02:31
URII:	http://shdl.mmu.edu.my/id/eprint/13205

Downloads

Edit (login required)